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

Ophthalmology Ophthalmology

DPN: Detail-Preserving Network with High Resolution Representation for Efficient Segmentation of Retinal Vessels

ArXiv Preprint

Retinal vessels are important biomarkers for many ophthalmological and cardiovascular diseases. It is of great significance to develop an accurate and fast vessel segmentation model for computer-aided diagnosis. Existing methods, such as U-Net follows the encoder-decoder pipeline, where detailed information is lost in the encoder in order to achieve a large field of view. Although detailed information could be recovered in the decoder via multi-scale fusion, it still contains noise. In this paper, we propose a deep segmentation model, called detail-preserving network (DPN) for efficient vessel segmentation. To preserve detailed spatial information and learn structural information at the same time, we designed the detail-preserving block (DP-Block). Further, we stacked eight DP-Blocks together to form the DPN. More importantly, there are no down-sampling operations among these blocks. As a result, the DPN could maintain a high resolution during the processing, which is helpful to locate the boundaries of thin vessels. To illustrate the effectiveness of our method, we conducted experiments over three public datasets. Experimental results show, compared to state-of-the-art methods, our method shows competitive/better performance in terms of segmentation accuracy, segmentation speed, extensibility and the number of parameters. Specifically, 1) the AUC of our method ranks first/second/third on the STARE/CHASE_DB1/DRIVE datasets, respectively. 2) Only one forward pass is required of our method to generate a vessel segmentation map, and the segmentation speed of our method is over 20-160x faster than other methods on the DRIVE dataset. 3) We conducted cross-training experiments to demonstrate the extensibility of our method, and results revealed that our method shows superior performance. 4) The number of parameters of our method is only around 96k, less then all comparison methods.

Song Guo


Cardiology Cardiology

A comparison of artificial intelligence-based algorithms for the identification of patients with depressed right ventricular function from 2-dimentional echocardiography parameters and clinical features.

In Cardiovascular diagnosis and therapy

Background : Recognizing low right ventricular (RV) function from 2-dimentiontial echocardiography (2D-ECHO) is challenging when parameters are contradictory. We aim to develop a model to predict low RV function integrating the various 2D-ECHO parameters in reference to cardiac magnetic resonance (CMR)-the gold standard.

Methods : We retrospectively identified patients who underwent a 2D-ECHO and a CMR within 3 months of each other at our institution (American University of Beirut Medical Center). We extracted three parameters (TAPSE, S' and FACRV) that are classically used to assess RV function. We have assessed the ability of 2D-ECHO derived parameters and clinical features to predict RV function measured by the gold standard CMR. We compared outcomes from four machine learning algorithms, widely used in the biomedical community to solve classification problems.

Results : One hundred fifty-five patients were identified and included in our study. Average age was 43±17.1 years old and 52/156 (33.3%) were females. According to CMR, 21 patients were identified to have RV dysfunction, with an RVEF of 34.7%±6.4%, as opposed to 54.7%±6.7% in the normal RV population (P<0.0001). The Random Forest model was able to detect low RV function with an AUC =0.80, while general linear regression performed poorly in our population with an AUC of 0.62.

Conclusions : In this study, we trained and validated an ML-based algorithm that could detect low RV function from clinical and 2D-ECHO parameters. The algorithm has two advantages: first, it performed better than general linear regression, and second, it integrated the various 2D-ECHO parameters.

Ahmad Ali, Ibrahim Zahi, Sakr Georges, El-Bizri Abdallah, Masri Lara, Elhajj Imad H, El-Hachem Nehme, Isma’eel Hussain


2D-ECHO, CMR, RV function, machine learning

Radiology Radiology

Machine learning-based CT fractional flow reserve assessment in acute chest pain: first experience.

In Cardiovascular diagnosis and therapy

Background : Computed tomography (CT)-derived fractional flow reserve (FFRCT) enables the non-invasive functional assessment of coronary artery stenosis. We evaluated the feasibility and potential clinical role of FFRCT in patients presenting to the emergency department with acute chest pain who underwent chest-pain CT (CPCT).

Methods : For this retrospective IRB-approved study, we included 56 patients (median age: 62 years, 14 females) with acute chest pain who underwent CPCT and who had at least a mild (≥25% diameter) coronary artery stenosis. CPCT was evaluated for the presence of acute plaque rupture and vulnerable plaque features. FFRCT measurements were performed using a machine learning-based software. We assessed the agreement between the results from FFRCT and patient outcome (including results from invasive catheter angiography and from any non-invasive cardiac imaging test, final clinical diagnosis and revascularization) for a follow-up of 3 months.

Results : FFRCT was technically feasible in 38/56 patients (68%). Eleven of the 38 patients (29%) showed acute plaque rupture in CPCT; all of them underwent immediate coronary revascularization. Of the remaining 27 patients (71%), 16 patients showed vulnerable plaque features (59%), of whom 11 (69%) were diagnosed with acute coronary syndrome (ACS) and 10 (63%) underwent coronary revascularization. In patients with vulnerable plaque features in CPCT, FFRCT had an agreement with outcome in 12/16 patients (75%). In patients without vulnerable plaque features (n=11), one patient showed myocardial ischemia (9%). In these patients, FFRCT and patient outcome showed an agreement in 10/11 patients (91%).

Conclusions : Our preliminary data show that FFRCT is feasible in patients with acute chest pain who undergo CPCT provided that image quality is sufficient. FFRCT has the potential to improve patient triage by reducing further downstream testing but appears of limited value in patients with CT signs of acute plaque rupture.

Eberhard Matthias, Nadarevic Tin, Cousin Andrej, von Spiczak Jochen, Hinzpeter Ricarda, Euler Andre, Morsbach Fabian, Manka Robert, Keller Dagmar I, Alkadhi Hatem


Acute coronary syndrome (ACS), computed tomography angiography, fractional flow reserve, machine learning, myocardial

General General

Insight into glycogen synthase kinase-3β inhibitory activity of phyto-constituents from Melissa officinalis: in silico studies.

In In silico pharmacology

Over activity of Glycogen synthase kinase-3β (GSK-3β), a serine/threonine-protein kinase has been implicated in a number of diseases including stroke, type II diabetes and Alzheimer disease (AD). This study aimed to find novel inhibitors of GSK-3β from phyto-constituents of Melissa officinalis with the aid of computational analysis. Molecular docking, induced-fit docking (IFD), calculation of binding free energy via the MM-GBSA approach and Lipinski's rule of five (RO5) were employed to filter the compounds and determine their druggability. Most importantly, the compounds pIC50 were predicted by machine learning-based model generated by AutoQSAR algorithm. The generated model was validated to affirm its predictive model. The best model obtained was Model kpls_desc_38 (R2 = 0.8467 and Q2 = 0.8069), and this external validated model was utilized to predict the bioactivities of the lead compounds. While a number of characterized compounds from Melissa officinalis showed better docking score, binding free energy alongside adherence to RO5 than co-cystallized ligand, only three compounds (salvianolic acid C, ellagic acid and naringenin) showed more satisfactory pIC50. The results obtained in this study can be useful to design potent inhibitors of GSK-3β.

Iwaloye Opeyemi, Elekofehinti Olusola Olalekan, Oluwarotimi Emmanuel Ayo, Kikiowo Babatom Iwa, Fadipe Toyin Mary


AutoQSAR, Glycogen synthase kinase-3β, Induced-fit docking (IFD), MM-GBSA, Melissa officinalis

General General

Listening forward: approaching marine biodiversity assessments using acoustic methods.

In Royal Society open science

Ecosystems and the communities they support are changing at alarmingly rapid rates. Tracking species diversity is vital to managing these stressed habitats. Yet, quantifying and monitoring biodiversity is often challenging, especially in ocean habitats. Given that many animals make sounds, these cues travel efficiently under water, and emerging technologies are increasingly cost-effective, passive acoustics (a long-standing ocean observation method) is now a potential means of quantifying and monitoring marine biodiversity. Properly applying acoustics for biodiversity assessments is vital. Our goal here is to provide a timely consideration of emerging methods using passive acoustics to measure marine biodiversity. We provide a summary of the brief history of using passive acoustics to assess marine biodiversity and community structure, a critical assessment of the challenges faced, and outline recommended practices and considerations for acoustic biodiversity measurements. We focused on temperate and tropical seas, where much of the acoustic biodiversity work has been conducted. Overall, we suggest a cautious approach to applying current acoustic indices to assess marine biodiversity. Key needs are preliminary data and sampling sufficiently to capture the patterns and variability of a habitat. Yet with new analytical tools including source separation and supervised machine learning, there is substantial promise in marine acoustic diversity assessment methods.

Mooney T Aran, Di Iorio Lucia, Lammers Marc, Lin Tzu-Hao, Nedelec Sophie L, Parsons Miles, Radford Craig, Urban Ed, Stanley Jenni


bioacoustics, ecosystem health, richness, soundscape

Radiology Radiology

Advancing COVID-19 differentiation with a robust preprocessing and integration of multi-institutional open-repository computer tomography datasets for deep learning analysis.

In Experimental and therapeutic medicine

The coronavirus pandemic and its unprecedented consequences globally has spurred the interest of the artificial intelligence research community. A plethora of published studies have investigated the role of imaging such as chest X-rays and computer tomography in coronavirus disease 2019 (COVID-19) automated diagnosis. Οpen repositories of medical imaging data can play a significant role by promoting cooperation among institutes in a world-wide scale. However, they may induce limitations related to variable data quality and intrinsic differences due to the wide variety of scanner vendors and imaging parameters. In this study, a state-of-the-art custom U-Net model is presented with a dice similarity coefficient performance of 99.6% along with a transfer learning VGG-19 based model for COVID-19 versus pneumonia differentiation exhibiting an area under curve of 96.1%. The above was significantly improved over the baseline model trained with no segmentation in selected tomographic slices of the same dataset. The presented study highlights the importance of a robust preprocessing protocol for image analysis within a heterogeneous imaging dataset and assesses the potential diagnostic value of the presented COVID-19 model by comparing its performance to the state of the art.

Trivizakis Eleftherios, Tsiknakis Nikos, Vassalou Evangelia E, Papadakis Georgios Z, Spandidos Demetrios A, Sarigiannis Dimosthenis, Tsatsakis Aristidis, Papanikolaou Nikolaos, Karantanas Apostolos H, Marias Kostas


COVID-19, artificial intelligence, deep learning analysis, multi-institutional data