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

Radiology Radiology

Artificial Intelligence and the Trainee Experience in Radiology.

In Journal of the American College of Radiology : JACR

The hype around artificial intelligence (AI) in radiology continues unabated, despite the fact that the exact role AI will play in future radiology practice remains undefined. Nevertheless, education of the radiologists of the future is ongoing and needs to account for the uncertainty of this new technology. Radiology residency training has evolved even before the recent advent of imaging AI. Yet radiology residents and fellows will likely one day experience the benefits of an AI-enabled clinical training. This will offer them a customized learning experience and the ability to analyze large quantities of data about their progress in residency, with substantially less manual effort than is currently required. Additionally, they will need to learn how to interact with AI tools in clinical practice, and more importantly, understand how to evaluate AI outputs in a critical fashion as yet another piece of information contributing to the interpretation of an imaging examination. Although the exact role AI will play in the future practice of radiology remains undefined, it will surely be integrated into the education of future radiologists.

Simpson Scott A, Cook Tessa S


Artificial intelligence, radiology education, radiology residency

General General

PROTAC-DB: an online database of PROTACs.

In Nucleic acids research ; h5-index 217.0

Proteolysis-targeting chimeras (PROTACs), which selectively degrade targeted proteins by the ubiquitin-proteasome system, have emerged as a novel therapeutic technology with potential advantages over traditional inhibition strategies. In the past few years, this technology has achieved substantial progress and two PROTACs have been advanced into phase I clinical trials. However, this technology is still maturing and the design of PROTACs remains a great challenge. In order to promote the rational design of PROTACs, we present PROTAC-DB, a web-based open-access database that integrates structural information and experimental data of PROTACs. Currently, PROTAC-DB consists of 1662 PROTACs, 202 warheads (small molecules that target the proteins of interest), 65 E3 ligands (small molecules capable of recruiting E3 ligases) and 806 linkers, as well as their chemical structures, biological activities, and physicochemical properties. Except the biological activities of warheads and E3 ligands, PROTAC-DB also provides the degradation capacities, binding affinities and cellular activities for PROTACs. PROTAC-DB can be queried with two general searching approaches: text-based (target name, compound name or ID) and structure-based. In addition, for the convenience of users, a filtering tool for the searching results based on the physicochemical properties of compounds is also offered. PROTAC-DB is freely accessible at

Weng Gaoqi, Shen Chao, Cao Dongsheng, Gao Junbo, Dong Xiaowu, He Qiaojun, Yang Bo, Li Dan, Wu Jian, Hou Tingjun


General General

A machine-learning-based method for prediction of macrocyclization patterns of polyketides and nonribosomal peptides.

In Bioinformatics (Oxford, England)

MOTIVATION : Even though genome mining tools have successfully identified large numbers of Nonribosomal Peptide Synthetase (NRPS) and Polyketide Synthase (PKS) biosynthetic gene clusters (BGCs) in bacterial genomes, currently no tool can predict the chemical structure of the secondary metabolites biosynthesized by these BGCs. Lack of algorithms for predicting complex macrocyclization patterns of linear PK/NRP biosynthetic intermediates has been the major bottleneck in deciphering the final bioactive chemical structures of PKs/NRPs by genome mining.

RESULTS : Using a large dataset of known chemical structures of macrocyclized PKs/NRPs, we have developed a machine learning (ML) algorithm for distinguishing the correct macrocyclization pattern of PKs/NRPs from the library of all theoretically possible cyclization patterns. Benchmarking of this ML classifier on completely independent datasets has revealed ROC-AUC and PR-AUC values of 0.82 and 0.81 respectively. This cyclization prediction algorithm has been used to develop SBSPKSv3, a genome mining tool for completely automated prediction of macrocyclized structures of NRPs/PKs. SBSPKSv3 has been extensively benchmarked on a dataset of over 100 BGCs with known PKs/NRPs products.

AVAILABILITY AND IMPLEMENTATION : The macrocyclization prediction pipeline and all the datasets used in this study are freely available at

SUPPLEMENTARY INFORMATION : Supplementary data are available at journal site online.

Agrawal Priyesh, Mohanty Debasisa


Genome Analysis, Genome mining, Machine Learning, Nonribosomal Peptides, Polyketides, Random Forest, macrocyclization

General General

Estimating 3-dimensional liver motion using deep learning and 2-dimensional ultrasound images.

In International journal of computer assisted radiology and surgery

PURPOSE : The main purpose of this study is to construct a system to track the tumor position during radiofrequency ablation (RFA) treatment. Existing tumor tracking systems are designed to track a tumor in a two-dimensional (2D) ultrasound (US) image. As a result, the three-dimensional (3D) motion of the organs cannot be accommodated and the ablation area may be lost. In this study, we propose a method for estimating the 3D movement of the liver as a preliminary system for tumor tracking. Additionally, in current 3D movement estimation systems, the motion of different structures during RFA could reduce the tumor visibility in US images. Therefore, we also aim to improve the estimation of the 3D movement of the liver by improving the liver segmentation. We propose a novel approach to estimate the relative 6-axial movement (x, y, z, roll, pitch, and yaw) between the liver and the US probe in order to estimate the overall movement of the liver.

METHOD : We used a convolutional neural network (CNN) to estimate the 3D displacement from two-dimensional US images. In addition, to improve the accuracy of the estimation, we introduced a segmentation map of the liver region as the input for the regression network. Specifically, we improved the extraction accuracy of the liver region by using a bi-directional convolutional LSTM U-Net with densely connected convolutions (BCDU-Net).

RESULTS : By using BCDU-Net, the accuracy of the segmentation was dramatically improved, and as a result, the accuracy of the movement estimation was also improved. The mean absolute error for the out-of-plane direction was 0.0645 mm/frame.

CONCLUSION : The experimental results show the effectiveness of our novel method to identify the movement of the liver by BCDU-Net and CNN. Precise segmentation of the liver by BCDU-Net also contributes to enhancing the performance of the liver movement estimation.

Yagasaki Shiho, Koizumi Norihiro, Nishiyama Yu, Kondo Ryosuke, Imaizumi Tsubasa, Matsumoto Naoki, Ogawa Masahiro, Numata Kazushi


Convolutional neural networks, Motion estimation, Radiofrequency ablation, U-Net, Ultrasound image

Public Health Public Health

Prognostic value of immune-related genes and immune cell infiltration analysis in the tumor microenvironment of head and neck squamous cell carcinoma.

In Head & neck ; h5-index 50.0

BACKGROUND : Head and neck squamous cell carcinoma (HNSCC) is one of the few malignant tumors that respond well to immunotherapy. We aimed to investigate the immune-related genes and immune cell infiltration of HNSCC and construct a predictive model for its prognosis.

METHODS : We calculated the stromal/immune scores of patients with HNSCC from The Cancer Genome Atlas using the Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data algorithm and investigated the relationship between the scores and patients' prognosis. Three machine learning algorithms (LASSO, Random Forest, and Rbsurv) were performed to screen key immune-related genes and constructed a predictive model. The immune cell infiltrating was calculated by the Tumor Immune Estimation Resource algorithm.

RESULTS : The stromal and immune scores significantly correlated with prognosis. A 6-gene signature was selected and displayed a robust predictive effect. The expressions of key genes were associated with immune infiltrating. GSE65858 validated the results.

CONCLUSION : Our study comprehensively analyzed the tumor microenvironment of HNSCC and constructed a robust predictive model, providing a basis for further investigation of therapy.

Wang Zizhuo, Yuan Huangbo, Huang Jia, Hu Dianxing, Qin Xu, Sun Chaoyang, Chen Gang, Wang Beibei


The Cancer Genome Atlas (TCGA), head and neck squamous cell carcinomas (HNSCCs), machine learning, prognosis, tumor immune microenvironment (TME)

General General

Deep neural network improves the estimation of polygenic risk scores for breast cancer.

In Journal of human genetics

Polygenic risk scores (PRS) estimate the genetic risk of an individual for a complex disease based on many genetic variants across the whole genome. In this study, we compared a series of computational models for estimation of breast cancer PRS. A deep neural network (DNN) was found to outperform alternative machine learning techniques and established statistical algorithms, including BLUP, BayesA, and LDpred. In the test cohort with 50% prevalence, the Area Under the receiver operating characteristic Curve (AUC) were 67.4% for DNN, 64.2% for BLUP, 64.5% for BayesA, and 62.4% for LDpred. BLUP, BayesA, and LPpred all generated PRS that followed a normal distribution in the case population. However, the PRS generated by DNN in the case population followed a bimodal distribution composed of two normal distributions with distinctly different means. This suggests that DNN was able to separate the case population into a high-genetic-risk case subpopulation with an average PRS significantly higher than the control population and a normal-genetic-risk case subpopulation with an average PRS similar to the control population. This allowed DNN to achieve 18.8% recall at 90% precision in the test cohort with 50% prevalence, which can be extrapolated to 65.4% recall at 20% precision in a general population with 12% prevalence. Interpretation of the DNN model identified salient variants that were assigned insignificant p values by association studies, but were important for DNN prediction. These variants may be associated with the phenotype through nonlinear relationships.

Badré Adrien, Zhang Li, Muchero Wellington, Reynolds Justin C, Pan Chongle