Deep Learning for Classification of Bone Lesions on Routine MRI.

BACKGROUND: Radiologists have difficulty distinguishing benign from malignant bone lesions because these lesions may have similar imaging appearances. The purpose of this study was to develop a deep learning algorithm that can differentiate benign and malignant bone lesions using routine magnetic resonance imaging (MRI) and patient demographics. METHODS: 1,060 histologically confirmed bone lesions with T1- and T2-weighted pre-operative MRI were retrospectively identified and included, with lesions from 4 institutions used for model development and internal validation, and data from a fifth institution used for external validation. Image-based models were generated using the EfficientNet-B0 architecture and a logistic regression model was trained using patient age, sex, and lesion location. A voting ensemble was created as the final model. The performance of the model was compared to classification performance by radiology experts. FINDINGS: The cohort had a mean age of 30±23 years and was 58.3% male, with 582 benign lesions and 478 malignant. Compared to a contrived expert committee result, the ensemble deep learning model achieved (ensemble vs. experts): similar accuracy (0·76 vs. 0·73, p=0·7), sensitivity (0·79 vs. 0·81, p=1·0) and specificity (0·75 vs. 0·66, p=0·48), with a ROC AUC of 0·82. On external testing, the model achieved ROC AUC of 0·79. INTERPRETATION: Deep learning can be used to distinguish benign and malignant bone lesions on par with experts. These findings could aid in the development of computer-aided diagnostic tools to reduce unnecessary referrals to specialized centers from community clinics and limit unnecessary biopsies. FUNDING: This work was funded by a Radiological Society of North America Research Medical Student Grant (#RMS2013) and supported by the Amazon Web Services Diagnostic Development Initiative.

Sentinel lymph node biopsy in early stage cervical cancer: A meta-analysis.

BACKGROUND: The aim of this study was to determine the specific side detection rate of the sentinel lymph node biopsy and the accuracy in predicting lymph node metastasis in early stage cervical cancer. METHODS: A systematic search of databases was performed from the inception of the databases to 27 June 2020. Studies of cervical cancer patients with FIGO stage FIGO ⅠA~ⅡB, evaluating the sentinel lymph node biopsy with blue dye, technetium 99, combined technique (blue dye with technetium 99) or indocyanine green with a reference standard of systematic pelvis lymph node dissection or clinical follow-up were included. Stata12.0 and Meta-Disc 1.4 were used for the meta-analysis. RESULTS: Of 2825 articles found, 21 studies (2234 women) were eventually included. Out of 21 studies, 20 met the detection rate evaluation criteria and six were included for sensitivity meta-analysis. Due to heterogeneity, it was inappropriate to pool all studies. The pooled specific side detection rates were 85% in tumors up to 2 cm, 67% in tumors over 2 cm, 75.2% for blue dye, 74.7% for technetium 99, 84% for combined technique, and 85.5% for indocyanine green. The sentinel lymph node biopsy had a pooled specific side sensitivity of 88%. Adverse effects of sentinel lymph node biopsy appear minimal for most patients and are mainly related to the injection of blue dye. CONCLUSIONS: Sentinel lymph node biopsy using a tracer with a high detection rate and ultrastaging is highly accurate and reliable when limited to seriously selected patients, with satisfactory bilateral lymph node mapping and where enough cases for learning curve optimization exist. Indocyanine green sentinel lymph node mapping seems to be a superior sentinel lymph node mapping technique compared to other methods at present.

Deep learning-based classification of primary bone tumors on radiographs: A preliminary study.

BACKGROUND: To develop a deep learning model to classify primary bone tumors from preoperative radiographs and compare performance with radiologists. METHODS: A total of 1356 patients (2899 images) with histologically confirmed primary bone tumors and pre-operative radiographs were identified from five institutions' pathology databases. Manual cropping was performed by radiologists to label the lesions. Binary discriminatory capacity (benign versus not-benign and malignant versus not-malignant) and three-way classification (benign versus intermediate versus malignant) performance of our model were evaluated. The generalizability of our model was investigated on data from external test set. Final model performance was compared with interpretation from five radiologists of varying level of experience using the Permutations tests. FINDINGS: For benign vs. not benign, model achieved area under curve (AUC) of 0•894 and 0•877 on cross-validation and external testing, respectively. For malignant vs. not malignant, model achieved AUC of 0•907 and 0•916 on cross-validation and external testing, respectively. For three-way classification, model achieved 72•1% accuracy vs. 74•6% and 72•1% for the two subspecialists on cross-validation (p = 0•03 and p = 0•52, respectively). On external testing, model achieved 73•4% accuracy vs. 69•3%, 73•4%, 73•1%, 67•9%, and 63•4% for the two subspecialists and three junior radiologists (p = 0•14, p = 0•89, p = 0•93, p = 0•02, p < 0•01 for radiologists 1-5, respectively). INTERPRETATION: Deep learning can classify primary bone tumors using conventional radiographs in a multi-institutional dataset with similar accuracy compared to subspecialists, and better performance than junior radiologists. FUNDING: The project described was supported by RSNA Research & Education Foundation, through grant number RSCH2004 to Harrison X. Bai.