Objectives: To develop and validate a deep learning (DL)-based primary tumor biopsy signature for predicting axillary lymph node (ALN) metastasis preoperatively in early breast cancer (EBC) patients with clinically negative ALN.Methods: A total of 1,058 EBC patients with pathologically confirmed ALN status were enrolled from May 2010 to August 2020. A DL core-needle biopsy (DL-CNB) model was built on the attention-based multiple instance-learning (AMIL) framework to predict ALN status utilizing the DL features, which were extracted from the cancer areas of digitized whole-slide images (WSIs) of breast CNB specimens annotated by two pathologists. Accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and areas under the ROC curve (AUCs) were analyzed to evaluate our model.Results: The best-performing DL-CNB model with VGG16_BN as the feature extractor achieved an AUC of 0.816 (95% confidence interval (CI): 0.758, 0.865) in predicting positive ALN metastasis in the independent test cohort. Furthermore, our model incorporating the clinical data, which was called DL-CNB+C, yielded the best accuracy of 0.831 (95%CI: 0.775, 0.878), especially for patients younger than 50 years (AUC: 0.918, 95%CI: 0.825, 0.971). The interpretation of DL-CNB model showed that the top signatures most predictive of ALN metastasis were characterized by the nucleus features including density (p= 0.015), circumference (p= 0.009), circularity (p= 0.010), and orientation (p= 0.012).Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.

Superb microvascular imaging (SMI) for depiction of microvascular flow in thyroid nodules was compared with color/power Doppler imaging (CDI/PDI) and contrast-enhanced ultrasonography (CEUS). In addition, the diagnostic performance of conventional ultrasound combined with SMI for differentiating benign and malignant thyroid nodules was evaluated. Preoperative conventional ultrasound consisting of gray-scale ultrasonography and CDI/PDI, followed by SMI and CEUS, was used to record 52 thyroid nodules. Two radiologists analyzed the gray-scale ultrasound signs and nodules’ microvascular flow patterns to differentiate between benign (n = 13) and malignant nodules (n = 39). SMI was significantly more effective in the detection of microvascular flow signals than CDI/PDI. In malignant nodules, SMI depicted the presence of incomplete surrounding periphery microvasculature and of disordered heterogeneous internal microvasculature. Benign nodules showed complete surrounding periphery microvasculature (ring sign) and homogeneity internal branching. The accuracies of conventional ultrasound combined with CDI/ PDI, SMI, or CEUS for predicting malignancy were 67.31, 86.54, and 92.31%, respectively. The accuracy of SMI differed significantly from CDI/PDI (P = 0.012), but not from CEUS (P = 0.339). Microvascular flow and vessel branching in the peripheral and internal microvasculature of thyroid nodules is depicted with greater detail and clarity with SMI compared with conventional ultrasound. SMI offers a safe and low-cost alternative to CEUS for differentiating between benign and malignant thyroid nodules.

Patients with ALK gene rearrangements often manifest dramatic responses to crizotinib, an ALK inhibitor. Accurate identification of patients with ALK-positive non-small cell lung cancer (NSCLC) is essential for the clinical application of ALK-targeted therapy. However, assessing EML4-ALK rearrangement in NSCLC remains challenging in routine pathology practice. The aim of this study was to compare the diagnostic accuracy of FISH, immunohistochemistry (IHC), and real-time quantitative RT-PCR (QPCR) methodologies for detection of EML4-ALK rearrangement in NSCLC and to appraise immunohistochemistry as a pre-screening tool. In this study, a total of 473 paraffin-embedded NSCLC samples from surgical resections and biopsies were analyzed by IHC with ALK antibody. ALK rearrangement was further confirmed by FISH and QPCR. ALK protein expression was detected in twenty patients (20/473, 4.2%). Of the 20 ALK-positive cases by IHC, 15 cases were further confirmed as ALK rearrangement by FISH, and 5 cases were not interpretable. Also, we evaluated 13 out of the 20 IHC-positive tissues by QPCR in additional to FISH, and found that 9 cases were positive and 2 cases were equivocal, whereas 2 cases were negative although they were positive by both IHC and FISH. The ALK status was concordant in 5 out of 8 cases that were interpretable by three methods. Additionally, none of the 110 IHC-negative cases with adenocarcinoma histology showed ALK rearrangements by FISH. Histologically, almost all the ALK -rearranged cases were adenocarcinoma, except that one case was sarcomatoid carcinoma. A solid signet-ring cell pattern or mucinous cribriform pattern was presented at least focally in all ALK-positive tumors. In conclusion, our findings suggested that ALK rearrangement was associated with ALK protein expression. The conventional IHC assay is a valuable tool for the pre-screening of patients with ALK rearrangement in clinical practice and a combination of FISH and QPCR is required for further confirmation.

Clinical trials have shown that epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) did not improve the survival of patients with EGFR-mutated non-small cell lung cancer (NSCLC) because of the high crossover of treatments. Realistically, the role of EGFR-TKIs in NSCLC with mutated EGFR is not well known. We retrospectively analysed data from patients with recurrent or metastatic NSCLC. Clinical prognostic factors were identified by Cox proportional hazards modelling. Among 503 patients, the median overall survival (OS) for all of patients was 11.7 months. Cox analysis showed that PS 0–1, recurrent disease, EGFR mutations, or EGFR-TKI treatment were associated with improved OS. In patients with EGFR-activating mutations, Cox analysis showed that patients with adenocarcinoma, recurrent disease, or EGFR-TKI treatment had significantly longer survival. Patients with EGFR-activating mutations who received EGFR-TKI therapy had a median OS of 24.3 months, which was significantly longer than those who had not received EGFR-TKI therapy (10.8 months). Patients with wild-type EGFR had a median OS of 9.7 months and Cox analysis showed that PS score and disease type were independent predictors. EGFR-TKI therapy is an independently prognostic factor for NSCLC with mutated EGFR. A more effective therapy is needed for patients with wild-type EGFR.

Background. Since circulating tumor DNA (ctDNA) offers clear advantages as a minimally invasive method for tumor monitoring compared with tumor tissue, we aimed to evaluate genotyping ctDNA using a next-generation sequencing- (NGS-) based panel to identify the prognostic value of mutation status in metastatic colorectal cancer (mCRC) patients with primary tumor resected and with subsequent lines of treatment in this study. Methods. 76 mCRC patients treated in Beijing Chao-Yang Hospital from 2011 to 2017 were enrolled. Genotyping of RAS/BRAF in tumor tissue and ctDNA was determined by ARMS PCR and with a 40-gene panel using NGS, respectively. Patient clinicopathologic features and RAS/BRAF gene mutation status were evaluated by survival analysis for disease-free survival (DFS) and progression-free survival (PFS). Results. Among 76 patients, KRAS distributions were not significantly correlated with any clinicopathologic features. The concordance between tumor tissue and ctDNA KRAS mutation was 81.25%. Mutations of RAS/BRAF had no significant impact on DFS after surgery (hazard ratio (HR), 1.205; 95% CI, 0.618 to 2.349; P=0.5837) but prognosticated poorer PFS in subsequent first-line therapy (HR, 3.351; 95% CI, 1.172 to 9.576; P=0.024). Conclusion. ctDNA was comparable with tumor tissue for mutation detection. RAS/BRAF mutations detected in ctDNA predict a worse PFS in mCRC patients with first-line chemotherapy. Our results provide support for the prognostic value of RAS/BRAF ctDNA mutation detection in mCRC patients.

Aggressive angiomyxoma (AAM) is a rare mesenchymal tumor that usually occurs in the pelvis and perineum of young females. AAM can simulate Bartholin's gland cyst, abscess, lipoma, simple labial cyst, or other pelvic soft tissue tumors. Here we present five cases of AAM with mean age of 42. The patients mainly presented slow-growing mass in the abdomen and perineum (3 cases in the pelvis, 1 in the vulva, and 1 in the buttock). Color Doppler flow imaging revealed blood flow for the 3 pelvic lesions. Enhanced computed tomography and magnetic resonance imaging of the other 2 cases showed the typical “swirled” or “layered” structure characteristic. Through the pathological examination, its positivity to estrogen and progesterone receptors can justify enlargement and recurrence, confirming the tumor is AAM. All 5 patients underwent local tumor resection. Two patients recurred 8 and 15 months after surgery, respectively. The longest follow-up was 42 months. Although few cases are reported, early recognition demands high index of suspicion for both gynaecologists and pathologists. Wide surgical excision with tumor free margins is the basis of curative treatment. Adjuvant therapy may be necessary for residual or recurrent tumors. Long-term follow-up is recommended.