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

Radiology Radiology

Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study.

In Oral radiology

OBJECTIVES : This study aimed to examine the performance of deep learning object detection technology for detecting and identifying maxillary cyst-like lesions on panoramic radiography.

METHODS : Altogether, 412 patients with maxillary cyst-like lesions (including several benign tumors) were enrolled. All panoramic radiographs were arbitrarily assigned to the training, testing 1, and testing 2 datasets of the study. The deep learning process of the training images and labels was performed for 1000 epochs using the DetectNet neural network. The testing 1 and testing 2 images were applied to the created learning model, and the detection performance was evaluated. For lesions that could be detected, the classification performance (sensitivity) for identifying radicular cysts or other lesions were examined.

RESULTS : The recall, precision, and F-1 score for detecting maxillary cysts were 74.6%/77.1%, 89.8%/90.0%, and 81.5%/83.1% for the testing 1/testing 2 datasets, respectively. The recall was higher in the anterior regions and for radicular cysts. The sensitivity was higher for identifying radicular cysts than for other lesions.

CONCLUSIONS : Using deep learning object detection technology, maxillary cyst-like lesions could be detected in approximately 75-77%.

Watanabe Hirofumi, Ariji Yoshiko, Fukuda Motoki, Kuwada Chiaki, Kise Yoshitaka, Nozawa Michihito, Sugita Yoshihiko, Ariji Eiichiro


Deep learning, Maxillary cysts, Object detection, Panoramic radiography, Radicular cysts

Surgery Surgery

Prediction of early recurrence of hepatocellular carcinoma after resection using digital pathology images assessed by machine learning.

In Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc

Hepatocellular carcinoma (HCC) is a representative primary liver cancer caused by long-term and repetitive liver injury. Surgical resection is generally selected as the radical cure treatment. Because the early recurrence of HCC after resection is associated with low overall survival, the prediction of recurrence after resection is clinically important. However, the pathological characteristics of the early recurrence of HCC have not yet been elucidated. We attempted to predict the early recurrence of HCC after resection based on digital pathologic images of hematoxylin and eosin-stained specimens and machine learning applying a support vector machine (SVM). The 158 HCC patients meeting the Milan criteria who underwent surgical resection were included in this study. The patients were categorized into three groups: Group I, patients with HCC recurrence within 1 year after resection (16 for training and 23 for test); Group II, patients with HCC recurrence between 1 and 2 years after resection (22 and 28); and Group III, patients with no HCC recurrence within 4 years after resection (31 and 38). The SVM-based prediction method separated the three groups with 89.9% (80/89) accuracy. Prediction of Groups I was consistent for all cases, while Group II was predicted to be Group III in one case, and Group III was predicted to be Group II in 8 cases. The use of digital pathology and machine learning could be used for highly accurate prediction of HCC recurrence after surgical resection, especially that for early recurrence. Currently, in most cases after HCC resection, regular blood tests and diagnostic imaging are used for follow-up observation; however, the use of digital pathology coupled with machine learning offers potential as a method for objective postoprative follow-up observation.

Saito Akira, Toyoda Hidenori, Kobayashi Masaharu, Koiwa Yoshinori, Fujii Hiroki, Fujita Koji, Maeda Atsuyuki, Kaneoka Yuji, Hazama Shoichi, Nagano Hiroaki, Mirza Aashiq H, Graf Hans-Peter, Cosatto Eric, Murakami Yoshiki, Kuroda Masahiko


Radiology Radiology

Deep Learning for Automated Liver Segmentation to Aid in the Study of Infectious Diseases in Nonhuman Primates.

In Academic radiology

With the advent of deep learning, convolutional neural networks (CNNs) have evolved as an effective method for the automated segmentation of different tissues in medical image analysis. In certain infectious diseases, the liver is one of the more highly affected organs, where an accurate liver segmentation method may play a significant role to improve the diagnosis, quantification, and follow-up. Although several segmentation algorithms have been proposed for liver or liver-tumor segmentation in computed tomography (CT) of human subjects, none of them have been investigated for nonhuman primates (NHPs), where the livers have a wide range in size and morphology. In addition, the unique characteristics of different infections or the heterogeneous immune responses of different NHPs to the infections appear with a diverse radiodensity distribution in the CT imaging. In this study, we investigated three state-of-the-art algorithms; VNet, UNet, and feature pyramid network (FPN) for automated liver segmentation in whole-body CT images of NHPs. The efficacy of the CNNs were evaluated on 82 scans of 37 animals, including pre and post-exposure to different viruses such as Ebola, Marburg, and Lassa. Using a 10-fold cross-validation, the best performance for the segmented liver was provided by the FPN; an average 94.77% Dice score, and 3.6% relative absolute volume difference. Our study demonstrated the efficacy of multiple CNNs, wherein the FPN outperforms VNet and UNet for liver segmentation in infectious disease imaging research.

Reza Syed M S, Bradley Dara, Aiosa Nina, Castro Marcelo, Lee Ji Hyun, Lee Byeong-Yeul, Bennett Richard S, Hensley Lisa E, Cong Yu, Johnson Reed, Hammoud Dima, Feuerstein Irwin, Solomon Jeffrey


CT, deep learning, infectious disease, liver, nonhuman primate, segmentation, whole-body

Radiology Radiology

Imaging of OA - From disease modification to clinical utility.

In Best practice & research. Clinical rheumatology

Multiple disease-modifying osteoarthritis drug (DMOAD) trials were done in the last two decades, but no pharmacological agent has yet been approved by regulatory agencies as an effective therapy to date. Given the fact that we have seen the recent discontinuation of several late-stage drug development trials, a careful strategy is needed in formulating a plan for a successful DMOAD trial - including the various roles of imaging. This narrative review article will summarize how imaging is utilized in osteoarthritis from the perspective of disease modification to clinical utility. We will describe how semi-quantitative and quantitative magnetic resonance imaging approaches have been deployed in DMOAD trials. We will then review the utility of musculoskeletal ultrasound in research and clinical settings. Finally, novel hybrid positron emission tomography/MRI techniques and current research using artificial intelligence will be discussed, focusing on original research. Older publications are included for the discussion of the previous DMOAD trials and other relevant topics where deemed appropriate.

Hayashi Daichi, Roemer Frank W, Eckstein Felix, Samuels Jonathan, Guermazi Ali


Clinical trials, DMOAD, MRI, Osteoarthritis

Surgery Surgery

Molecular T-cell‒mediated rejection in transbronchial and mucosal lung transplant biopsies is associated with future risk of graft loss.

In The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation

BACKGROUND : We previously developed molecular assessment systems for lung transplant transbronchial biopsies (TBBs) with high surfactant and bronchial mucosal biopsies, identifying T-cell‒mediated rejection (TCMR) on the basis of the expression of rejection-associated transcripts, but the relationship of rejection to graft loss is unknown. This study aimed to develop molecular assessments for TBBs and mucosal biopsies and to establish the impact of molecular TCMR on graft survival.

METHODS : We used microarrays and machine learning to assign TCMR scores to an expanded cohort of 457 TBBs (367 high surfactant plus 90 low surfactant) and 314 mucosal biopsies. We tested the score agreement between TBB-TBB, mucosal-mucosal, and TBB-mucosal biopsy pairs in the same patient. We also assessed the association of molecular TCMR scores with graft loss (death or retransplantation) and compared it with the prognostic associations for histology and donor-specific antibodies.

RESULTS : The molecular TCMR scores assigned in all the TBBs performed similarly to those in high-surfactant TBBs, indicating that variation in alveolation in TBBs does not prevent the detection of TCMR. Mucosal biopsy pieces showed less piece-to-piece variation than TBBs. TCMR scores in TBBs agreed with those in mucosal biopsies. In both TBBs and mucosal biopsies, molecular TCMR was associated with graft loss, whereas histologic rejection and donor-specific antibodies were not.

CONCLUSIONS : Molecular TCMR can be detected in TBBs regardless of surfactant and in mucosal biopsies, which show less variability in the sampled tissue than TBBs. On the basis of these findings, molecular TCMR appears to be an important predictor of the risk of future graft failure.


Halloran Kieran, Parkes Michael D, Timofte Irina, Snell Gregory, Westall Glen, Havlin Jan, Lischke Robert, Hachem Ramsey, Kreisel Daniel, Levine Deborah, Kubisa Bartosz, Piotrowska Maria, Juvet Stephen, Keshavjee Shaf, Jaksch Peter, Klepetko Walter, Hirji Alim, Weinkauf Justin, Halloran Philip F


graft loss, lung biopsy, lung transplant, microarray, rejection

General General

Electroencephalography Might Improve Diagnosis of Acute Stroke and Large Vessel Occlusion.

In Stroke ; h5-index 83.0

BACKGROUND AND PURPOSE : Clinical methods have incomplete diagnostic value for early diagnosis of acute stroke and large vessel occlusion (LVO). Electroencephalography is rapidly sensitive to brain ischemia. This study examined the diagnostic utility of electroencephalography for acute stroke/transient ischemic attack (TIA) and for LVO.

METHODS : Patients (n=100) with suspected acute stroke in an emergency department underwent clinical exam then electroencephalography using a dry-electrode system. Four models classified patients, first as acute stroke/TIA or not, then as acute stroke with LVO or not: (1) clinical data, (2) electroencephalography data, (3) clinical+electroencephalography data using logistic regression, and (4) clinical+electroencephalography data using a deep learning neural network. Each model used a training set of 60 randomly selected patients, then was validated in an independent cohort of 40 new patients.

RESULTS : Of 100 patients, 63 had a stroke (43 ischemic/7 hemorrhagic) or TIA (13). For classifying patients as stroke/TIA or not, the clinical data model had area under the curve=62.3, whereas clinical+electroencephalography using deep learning neural network model had area under the curve=87.8. Results were comparable for classifying patients as stroke with LVO or not.

CONCLUSIONS : Adding electroencephalography data to clinical measures improves diagnosis of acute stroke/TIA and of acute stroke with LVO. Rapid acquisition of dry-lead electroencephalography is feasible in the emergency department and merits prehospital evaluation.

Erani Fareshte, Zolotova Nadezhda, Vanderschelden Benjamin, Khoshab Nima, Sarian Hagop, Nazarzai Laila, Wu Jennifer, Chakravarthy Bharath, Hoonpongsimanont Wirachin, Yu Wengui, Shahbaba Babak, Srinivasan Ramesh, Cramer Steven C


brain, deep learning, early diagnosis, electroencephalography, transient ischemic attack